People who administer servers or write code spend much of the day in the terminal: the text window where you type commands to make the computer work. Many assistants based on artificial intelligence, by contrast, live in the browser or inside the editor. So there’s a constant jump between the place where the work happens and the place where you ask for help. Gemini CLI, announced by Google on June 25, 2025, tries to remove that jump: it brings an AI assistant into the terminal, where the work actually happens.

What Gemini CLI is

Let’s start with the terms. CLI stands for command-line interface: the way of using a program by typing text commands instead of clicking buttons. An AI agent is a program that, beyond answering questions, can take concrete actions on your behalf: reading files, running commands, looking things up.

Gemini CLI combines the two. You install it on your own computer, launch it from the terminal, and talk to it in plain language, the way you’d write to a colleague. Behind the scenes it uses Gemini, Google’s family of AI models. At launch the assistant runs on Gemini 2.5 Pro, a model with a context window of one million tokens, later joined by the next generation covered in Gemini 3.

That last point is worth explaining. A token is a small chunk of text, roughly a syllable or a short word; the context window is how much text the model can keep in mind within a single conversation. One million tokens is a lot: it means you can hand the model entire projects, long log files, or extensive documentation without splitting them up by hand.

What it can do

The announcement and the documentation describe a general-purpose assistant, not one tied to a single task. The main things it can do:

• Read and understand the code of a project, explain it, and suggest changes.
• Run commands in the terminal and edit files, always in the folder you’re working in.
• Search the web through Google Search to ground its answers in current information, rather than only on the knowledge it was trained with.
• Follow written instructions: you can create a file called GEMINI.md with rules and context specific to the project, so the assistant keeps them in mind, an idea close to that of Agent Skills.

Two features deserve attention because they matter most to people working with servers.

The first is support for MCP, short for Model Context Protocol. It’s an open standard, built to connect AI assistants to external tools and data sources in a uniform way. In practice MCP acts as a universal plug: it lets you give Gemini CLI the ability to talk to other systems (a database, an internal service, a company API) without reinventing the connection each time.

The second is non-interactive use. Beyond the conversational mode, the assistant can be called from within a script by passing it the request directly. That makes it a piece you can build into automation, not only a tool to use by hand.

# Run it without installing anything permanently
npx @google/gemini-cli

# Single request, no interface, suited to scripts
gemini -p "Explain the architecture of this project"

# JSON output, easier to process automatically
gemini -p "List the defined services" --output-format json

Open source, with a caveat

The code for Gemini CLI is published on GitHub under the Apache 2.0 license. It’s a widely used permissive open source license: it lets you use, modify, and redistribute the program, including in commercial settings, with minimal obligations. In practice that means anyone can read the code to understand what it does, report problems, propose fixes, or adapt it to their own needs. For a tool that runs commands on your computer, being able to inspect the code is not a minor detail.

An honest caveat is needed, though, because the phrase “open source” here covers one part only. What’s open is the program you install locally, that is, the agent. The Gemini model, on the other hand, remains a Google service running in its data centers: it isn’t open source and can’t be downloaded. Put differently, the requests and the context (the text, the code, the files you share) are sent to Google’s servers to be processed. The computation happens in the cloud, not on your own computer.

What it costs and the usage limits

At launch Google offers free access tied to your personal Google account. The stated limits are 60 requests per minute and 1,000 requests per day, at no charge. The free package also includes a basic Gemini Code Assist license, the code-assistance service from the same family.

For those who need more - a company, say, or heavy use - there are paid alternatives: you can use Google AI Studio or Vertex AI keys, with usage-based billing, or the Gemini Code Assist Standard and Enterprise licenses. The free version is enough to try it out and for personal use; past a certain threshold you move to a paid plan.

Why it matters to admins and developers

The value isn’t in the novelty itself, but in where the tool sits. People who run systems already have the terminal open: having an assistant right there avoids switching context. Some practical uses that come up in day-to-day work:

• Getting an error message or a chunk of a log file explained without pasting it somewhere else.
• Getting a draft command or configuration to review, instead of writing it from scratch.
• Quickly making sense of a project inherited from someone else, by asking for a description of its structure.
• Building a request to the assistant into a script, using the non-interactive mode.

Being open source and based on an open standard like MCP also reduces the risk of being locked into a single vendor for the client side: the program can be read, adapted, and, in principle, connected to other tools.

Limits and cautions

Before adopting it, a few points are worth keeping in mind, without hype.

It’s in preview. Google describes it as a preview release: it may contain bugs, changing behavior, and features that aren’t yet stable. It’s not the thing to build critical processes on without a fallback.

Data leaves your computer. Because the model runs in the cloud, whatever you share with the assistant is sent to Google. For confidential content - proprietary code, credentials, customer data - that’s something to weigh carefully and to govern by your own policies, also in light of what GDPR requires on the infrastructure side.

It runs commands and edits files. That’s its strength, but also its risk. An agent that can launch commands needs supervision: it’s wise to review what it proposes before authorizing it, especially on production systems.

It can be wrong. Like any model of this kind, it sometimes produces incorrect or made-up answers. Treat the output as a draft to verify, not as truth to apply as-is.

In short

Gemini CLI is an AI agent that lives in the terminal: it reads code, runs commands, searches the web, and can be called from within scripts. The program is open source under the Apache 2.0 license, while the Gemini model that powers it remains a service in Google’s cloud. There’s a free plan with generous limits and paid options for heavier use. It’s useful because it puts the assistant where admins and developers already work, but it should be used with judgment: it’s in preview, it sends data to the cloud, and it can take actions on the system. One more tool, to be kept under control, not an autopilot.

Sources

• Introducing Gemini CLI: your open-source AI agent - The Keyword, Google
• google-gemini/gemini-cli - GitHub